{"id":"W6966799482","doi":"10.48410/m2ae-vj76","title":"Supplementary code data files for the thesis \"A Population-Based Approach to Genomic Island Analysis\"","year":2023,"lang":"en","type":"dataset","venue":"Summit, the SFU Research Repository","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Contig; Genome; ENCODE; Pathogenicity island; Population; Cluster analysis; Data integration; Source code; Genomics; Salmonella enterica","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003455249,0.001454504,0.001368892,0.003043658,0.001806912,0.003583337,0.004106802,0.001717805,0.7391768],"category_scores_gemma":[0.02647227,0.001176455,0.001668257,0.006013292,0.000693691,0.002676024,0.00360436,0.002192354,0.3458146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001292816,"about_ca_system_score_gemma":0.003666629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005449807,"about_ca_topic_score_gemma":0.007763757,"domain_scores_codex":[0.9982173,0.0003342319,0.0001919614,0.0005076045,0.0005917837,0.0001570889],"domain_scores_gemma":[0.9877986,0.006006286,0.0008529908,0.001598604,0.002899382,0.0008441859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001809334,0.00006380272,0.0008367276,0.001541517,0.00003597802,0.00008396056,0.00007448759,0.000745801,0.001203673,0.003017243,0.9733599,0.01885604],"study_design_scores_gemma":[0.0003107245,0.00009665784,0.003930073,0.0006160195,0.00004922273,0.0001896708,0.0001498043,0.002296983,0.001906585,0.01142625,0.9789531,0.00007477656],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0006701829,0.0002499406,0.01577209,0.0008904123,0.001071473,0.0004324707,0.95908,0.007814937,0.0140185],"genre_scores_gemma":[0.007470291,0.0008210147,0.04842205,0.001901092,0.0004889164,0.002595663,0.8970601,0.009263211,0.03197774],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7391768,"threshold_uncertainty_score":0.3720327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1589014451028148,"score_gpt":0.4038139880482954,"score_spread":0.2449125429454805,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}